Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    attends to the token "people" from related tokens indicating actions or attributes associated with "people."

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.41
    3:0.08
    4:0.09
    5:0.10
    6:0.12
    7:0.11
    Negative Logits
     Jurí
    -0.29
    si
    -0.29
    st
    -0.29
     orch
    -0.27
     sarili
    -0.27
     auffi
    -0.27
     pescoço
    -0.27
     LXXX
    -0.26
     concorso
    -0.26
     età
    -0.26
    POSITIVE LOGITS
    ioutil
    0.40
     Мексичка
    0.36
    ersdorf
    0.35
    出版年
    0.35
    tvguidetime
    0.34
    </tfoot>
    0.34
    $.}
    0.34
    .*")]
    0.33
    ')):
    0.33
    othea
    0.32
    Act Density 0.950%

    No Known Activations